Foliar Image Color Features for Rubber Nitrogen Deficiency Status Analysis

Abstract:

Many researchers have shown for decades that there is strong correlation between foliar color and its nitrogen nutrition status. However, their results also proved the big difference of this correlation among different crops or plants. In this paper, foliar image color features especially for rubber nitrogen nutrition status analysis are presented by comparative studies on current color feature indexes. Experimental results have shown that the ratio of red or green component to the blue component with detection rate of more than 98% is more suitable for rubber nitrogen nutrition analysis than any other correlations.

• Periodical: Advanced Materials Research (Volumes 488-489)
• Pages: 1674-1679
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.488-489.1674
• Online since: March 2012
• Authors: Xiao Ming Yao, Wei Luo
• Keywords: Correlation Modeling, Feature Extraction, Image-Based Analysis, Rubber Nitrogen Nutrition Status

References

[1] K. Inada: Studies on a Method for Determining the Deepness of Green and Color Chlorophyll Content of Intact Crop Leaves and Its Practical Applications. I. Principle for estimating the deepness of green color and chlorophyll content of whole leaves, Proceedings of the Crop Science Society of Japan, Vol.32, 1963, pp.157-162

DOI: 10.1626/jcs.32.157

[2] H. M. Benedict, and R. Swidler: Nondestructive Method for Estimating Chlorophyll Content of Leaves, Science, Vol.133, No.3469, 1961, pp.2015-2016

DOI: 10.1126/science.133.3469.2015

[3] K. Inada: Spectral Ratio of Reflectance for Estimating Chlorophyll Content of Leave, Japenese Journal of Crop Science, Vol. 54, No.3, 1985, pp.261-265

DOI: 10.1626/jcs.54.261

[4] V. K. Choubey, and Rani Choubey: Spectral Reflectance, Growth and Chlorophyll Relationships for Rice Crop in a Semi-Arid Region of India, Water Resources Management, Vol. 13, 1999, pp.73-84

[5] Y.-J. Lee, C.-M. Yang, K.-W. Chang, and Y. Shen: A Simple Spectral Index Using Reflectance of 735 nm to Assess Nitrogen Status of Rice Canopy, Agronomy Journal, Vol.100, No.1, 2008, pp.205-212

DOI: 10.2134/agronj2007.0018

[6] C.W. Wood, D.W. Reeves, and D.G. Himelrick: Relationships between chlorophyll meter reading and leaf chlorophyll concentration, N status, and crop yield: A review, Proc. Agron. Soc. Vol.23, New Zealand, 1993, pp.1-9

[7] F. J. Adamsen, P. J. Jr. Pinter, E. M. Barnes, R. L. LaMorte, G. W. Wall, S. W .Leavitt, and B. A. Kimball: Measuring Wheat Senescence Using a Digital Camera, Crop Science, Vol.39, 1999, pp.719-724

DOI: 10.2135/cropsci1999.0011183x003900030019x

[8] P. C. Scharf, and J. A. Lory: Calibrating Corn Color from Aerial Photographs to Predict Sidedress Nitrogen Need, Agronomy Journal, Vol.94, 2002, pp.397-404

DOI: 10.2134/agronj2002.3970

[9] W. Liu, S. Mao, Y. Li, Y. Han, X. Wang, G. Wang, Z. Fang, and P. Li: Color based Cotton Leaf Nitrogen Content Estimation, China Cotton, Vol.34, No.11, 2007, pp.22-23 (in Chinese)

[10] Y. Zhang, H. Mao, X. Zhang, and D. Zhao: Nitrogen Information Measurement of Canola Leaves Based on Multispectral Vision, Journal of Agricultural Mechanization Research, Vol.31, No.11, 2009, pp.83-85 (in Chinese)

[11] C. Hu, and P. Li: Application of image processing to diagnose cucumbers short of Mg and N, Journal of Jiangsu University (Natural Science Edition), Vol..25, No.1, 2004, pp.9-12 (in Chinese)

[12] H. Mao, G. Xu, and P. Li: Diagnosis of Nutrient Deficiency of Tomato Based on Computer Vision, Transactions of the Chinese Society for Agricultural Machinery, Vol.34, No.2, 2003, pp.73-75(in Chinese)

[13] X. Yao, W. Luo, and Z. Yuan: An Adaptive and Quantitative Rubber Nutrient Status Analyzing System by Digital Foliar Images, Proc. Of The 3rd IEEE International Congress on Image and Signal Processing (CISP 2010), Yantai, China, Oct. 16-18, 2010, pp.2492-2495

DOI: 10.1109/cisp.2010.5647929

[14] X. Yao, W. Du, S. Feng, and J. Zhou: Image-based Plant Nutrient Status Analysis: An Overview, Proc. Of IEEE International Conf. on Intelligent Computing and Intelligent Systems (ICIS2010), Xiamen, China, Oct. 29-31, 2010, pp.460-464

DOI: 10.1109/icicisys.2010.5658601